Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 5447
    Prev
    Next
    INDEX
    Explanations

    technical terms and components related to software programming and interfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    controller, interface, hdr definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.96
     esternos
    -0.80
    
    -0.79
    OGND
    -0.78
     gyhoeddwyd
    -0.77
    ScopeManager
    -0.77
     otomatig
    -0.76
     iNdEx
    -0.76
    featureID
    -0.75
    <pad>
    -0.74
    POSITIVE LOGITS
     typelib
    0.31
     Kassen
    0.31
    ByPrimaryKey
    0.28
     avenir
    0.27
     paragraphe
    0.26
    Director
    0.24
    ,
    0.24
     mourut
    0.24
    UserController
    0.23
     Bereichen
    0.23
    Activations Density 0.033%

    No Known Activations